SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1805.10522 · 2018

Calibrating Deep Convolutional Gaussian Processes

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1805.10522.json · badge: /api/ran/1805.10522.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
GiaLacTRAN/convolutional_deep_gp_random_features community (classifier label)
classifier basis not recorded on the link
2 ran · 3 no recorded run
FunctionStatusWhere it lives
find_conf_acc Ran
ran on a synthesized input
GiaLacTRAN/convolutional_deep_gp_random_features/code/utils.py
code served (permissive licence) · get_code("d561e6db5115b705")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - true_false: needs to be indexable, contains boolean/numeric values (used in acc = acc + true_false[i])
# - predicted_probs: needs to be indexable, contains numeric values (compared with lower/upper, added to conf)
# - lower: numeric value for comparison
# - upper: numeric value for comparison

# Create sample data
true_false = [1, 0, 1, 1, 0, 1]  # Binary labels (1 for correct, 0 for incorrect)
predicted_probs = [0.2, 0.45, 0.65, 0.75, 0.85, 0.95]  # Confidence scores between 0 and 1
lower = 0.4
upper = 0.8

ARGS = {
    "true_false": true_false,
    "predicted_probs": predicted_probs,
    "lower": lower,
    "upper": upper
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
one_hot_encoding Ran
ran on a synthesized input
GiaLacTRAN/convolutional_deep_gp_random_features/code/utils.py
code served (permissive licence) · get_code("696d4711f20fdcc6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct arguments for one_hot_encoding
# The function takes:
# - a: array-like of class indices (integers)
# - nb_class: number of classes (int)

# Create a small array of class indices
a = np.array([0, 1, 2, 1])  # 4 samples with class indices in range [0, 2]

# Number of classes
nb_class = 3

ARGS = {
    'a': a,
    'nb_class': nb_class
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_binary_scaling_vector Not yet run
unverified (harvested, no recorded run)
GiaLacTRAN/convolutional_deep_gp_random_features/code/exp.py
code served (permissive licence) · get_code("b17629d304ab95b2")
How it ran

no invocation recorded.

create_mask Not yet run
unverified (harvested, no recorded run)
GiaLacTRAN/convolutional_deep_gp_random_features/code/exp.py
code served (permissive licence) · get_code("5a26dc00098d0f54")
How it ran

no invocation recorded.

logsumexp Not yet run
unverified (harvested, no recorded run)
GiaLacTRAN/convolutional_deep_gp_random_features/code/utils.py
code served (permissive licence) · get_code("90a47165c25ec08f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The wide adoption of Convolutional Neural Networks (CNNs) in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in their predictions. Previous work on combining CNNs with Gaussian processes (GPs) has been developed under the assumption that the predictive probabilities of these models are well-calibrated. In this paper we show that, in fact, current combinations of CNNs and GPs are miscalibrated. We proposes a novel combination that considerably outperforms previous approaches on this aspect, while achieving state-of-the-art performance on image classification tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1805.10522")
get_code_for_paper("1805.10522")
have("1805.10522")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1805.10522.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1805.10522.svg)](https://syntology.ai/paper/1805.10522)

Connect an agent — have() is free.